Open AccessImprovement for distortion resistance of Delaunay triangulation net‐based fingerprint templates
Author(s) -
Li Zhaozheng,
Lei Weimin,
Zhang Wei
Publication year - 2019
Publication title -
iet biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.434
H-Index - 28
ISSN - 2047-4946
DOI - 10.1049/iet-bmt.2018.5263
Subject(s) - delaunay triangulation , distortion (music) , computer science , fingerprint (computing) , triangulation , bowyer–watson algorithm , artificial intelligence , fingerprint verification competition , computer vision , fingerprint recognition , algorithm , mathematics , telecommunications , geometry , amplifier , bandwidth (computing)
Fingerprint template is considered as an effective method to solve the problem of fingerprint protection, and an indispensable key technology in the identification field. Among them, the Delaunay triangulation net‐based template is a new type of solution. However, such a triangulation net is greatly affected by the elastic distortion of the fingerprint. In this study, a novel improvement, Delaunay tentacle, is proposed to this issue. Based on the orderly degradation of the Delaunay triangulation net, the Delaunay tentacle, kernel, and centre can be generated in turn. By calculating the deformation of the tentacles, this innovative, improved Delaunay triangulation structure can sense and resist distortion. The proposed algorithm is tested on the Fingerprint Verification Competition databases, and the model is compared with other current similar schemes. Experimental results demonstrate that it has promising performance.